INDEX

Explanations

comparative phrases indicating amounts or levels that are below a certain threshold

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 feroit

-0.54

 klientów

-0.50

oneofs

-0.47

 inneces

-0.47

 avoient

-0.46

 spół

-0.46

 pelanggan

-0.46

 ainfi

-0.45

 navideña

-0.45

 çift

-0.44

POSITIVE LOGITS

 Below

0.72

Below

0.69

 below

0.67

 NSCoder

0.65

$<

0.64

 BELOW

0.63

below

0.61

(<

0.58

LessThan

0.58

未満

0.57

Activations Density 0.452%

comparative phrases indicating amounts or levels that are below a certain threshold

No Comments

No Known Activations